Dynamic gesture recognition using millimeter-wave radar has a broad application prospect in the industrial Internet of Things (IoT) field. However, the existing methods in the random dynamic interference environment, such as throwing objects and waving and easily cause wrong recognition. This article proposes a dynamic gesture recognition method based on a convolutional neural network (CNN)-Transformer network to solve this problem. First, we reshape the original echoes acquired by the frequency-modulated continuous-wave (FMCW) millimeter-wave radar into 3-D data blocks in terms of Chirps $\times $ Samples $\times $ Frames. And we employ the mean elimination method to eliminate the static interference. Second, we extract dynamic gestures’ distance and Doppler information with the 2-D fast Fourier transform and obtain the range-time map and Doppler-time maps. And we employ the coherent accumulation method to improve the signal-to-noise ratio (SNR). Third, we construct the CNN-Transformer network model for dynamic gesture recognition. The CNN is used to extract the local features of gestures, and multiple Transformer modules are stacked to extract deeper effective features. Finally, we build a data set for gesture recognition, including six kinds of dynamic gestures and two kinds of random interference. The experimental results show that the proposed method has a gesture recognition accuracy of more than 98% and 96% in the noninterference scene and the random dynamic interference scene, respectively, which are superior to the conventional recognition methods.

In this letter, we investigate covert communication in relay networks with relay selection. We consider the scenario that while forwarding the source’s message, the selected relay opportunistically transmits its own message to the destination covertly. We derive the probability of detection error (PDE) and the average covert rate (ACR) in a closed form, based on which we analyse the effects of system parameters on the performance of the covert communication. Our analysis indicates that applying relay selection causes a decrease in the PDE, however, it can provide an ACR gain when the transmission rate of the source increases.

In this paper, we use directional antenna arrays instead of large-scale antenna arrays to combat the severe propagation path loss, and propose a novel beam channel model for millimeter-wave (mmWave) unmanned aerial vehicle (UAV) multiple-input multiple-output (MIMO) communication systems. The sparsity of mmWave channel and the directivity gain of mmWave antenna arrays are considered in the proposed model, and the antenna directivity gain is affected by the beamwidth, i.e., the narrower the beam, the higher the antenna directivity gain. Also, the beamwidth affects the number of active clusters, i.e., the wider the beam, the more the active clusters. Based on the proposed beam channel model, the influence of antenna directivity gain on the channel statistical characteristics including space-time correlation, frequency correlation function, and achievable rate is investigated. It is found that the directional antenna arrays can reduce Doppler spread caused by the movement of UAV and receiver and the mmWave communication systems using directional antenna arrays with high directivity gains can achieve an equivalent performance gain to that of the mmWave communication systems using omni-directional large-scale antenna arrays. Furthermore, considering the correlation between transmit and receive antenna elements, we obtain a closed-form expression of the tight upper bound of achievable rate, which is validated by using previously reported analytical upper bound and the simulation results.

Intelligent reflecting surface (IRS) composed of a large number of low-cost passive reflecting elements has attracted significant attention from communication communities because of its ability to substantially improve the communication performance. In this paper, the aperture area and radiation pattern of the IRS reflecting elements are considered, and a novel geometry-based three-dimensional (3-D) wideband channel model is proposed for IRS-assisted unmanned aerial vehicle (UAV) communication systems. In the proposed model, the reflection phase is designed by jointly considering the aperture area of the IRS reflecting element and the propagation phases among UAV, IRS, and receiver (Rx), each IRS reflecting element is modeled as an anomalous reflector instead of a specular reflector, and large-scale IRS reflecting elements can jointly beamform the signal in a desired direction. Based on the proposed model, the effects of arbitrary trajectory of UAV and the number and the size of passive reflecting elements on channel statistical characteristics are considered, and the average received signal power and the ergodic sum capacity, which consider the impacts of the number and the size of passive reflecting elements, are also investigated. Furthermore, the path loss of the IRS-assisted link, which is in inverse proportion to the square of aperture area of IRS reflecting elements, is derived, and it coincides with the measured results in real outdoor scenarios. Analysis shows that the communication performance can be enhanced by increasing the number and the size of IRS reflecting elements, and it is validated by numerical results and Monte-Carlo simulation results.

The navigation accuracy of the ship can be improved by associating the output tracks of radar with that of the automatic identification system (AIS). The traditional association method only uses the track features (including position, speed, and heading angle) and has low association accuracy and weak scene adaptability. We integrate the track and scene features through deep learning to associate the radar and AIS output tracks. Firstly, we employ the auto-encoder to reduce the noise of the original track data. The statistical distances of the two tracks in position, speed, and heading are obtained as the new track data. We map the track data to the high-dimensional space to extract the track features through the fully connected and dropout layers. Then, we reconstruct the scene data using the Euclidean distances of all tracks in position. The scene data is input into the three-dimensional (3D) convolutional and max-pooling layers to extract the scene features. Finally, we fuse the track and scene features in the channel dimension by the concatenated layer and use the fully connected layer to estimate the probability of two tracks coming from the same target. The simulation results demonstrate that the proposed method has better scene adaptability and higher association accuracy than the traditional methods.

In this article, a nonstationary 3-D wideband geometry-based stochastic model (GBSM) is proposed for low-altitude unmanned aerial vehicle (UAV) multiple-input–multiple-output (MIMO) communication systems. The proposed GBSM is a combination of Line-of-Sight (LoS) components, local multipath components (MPCs) scattering from the scatterers around the receiver (Rx), named as local scatterers, and far MPCs scattering from far scatterers, defined as not local scatterers, and uses 2-D one-ring and 3-D cylinder to mimic local scatterers as well as 3-D multiple confocal elliptic cylinders to mimic far scatterers. In this article, two-state continuous-time Markov chains (CTMCs) are introduced to model appearances or disappearances of the LoS components, local MPCs at the transmitter (Tx) installed on UAV, and far MPCs at the Tx and Rx, and the evolution process of the far MPCs is also investigated. The concept of the visibility region (VR) is introduced to model the birth and death processes of the local MPCs at the Rx, and the effect of the size of the VR on channel statistics is also considered. In the proposed GBSM, the inherited nature of the LoS components, the local MPCs and far MPCs, is considered, and the corresponding statistical properties are derived. The proposed nonstationary 3-D GBSM is validated by the measured results in terms of temporal correlation, and the numerical results show that the proposed 3-D GBSM is suitable for describing nonstationarity of the 3-D UAV-MIMO channel.